mlsanityData to 7 Oct 2026

SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving

arXiv 2404.06892 ↗First posted 10 Apr 2024cs.CVcited by 46

On the map: End-to-end autonomous driving → End-to-end system architecture

Abstract (arXiv)

End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any dense BEV representation. Concretely, we design a unified sparse architecture for perception tasks including detection, tracking, and online mapping. Moreover, we revisit motion prediction and planning, and devise a more justifiable motion planner framework. On the challenging nuScenes dataset, SparseAD achieves SOTA full-task performance among end-to-end methods and significantly narrows the performance gap between end-to-end paradigms and single-task methods. Codes will be released soon.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 80 of its 106 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

80 of 106 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?5 Dec
  2. 2023FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving2 Aug
  3. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving1 Aug
  4. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving10 May
  5. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning15 Jul
  6. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline16 Jun
  7. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving31 May

Other references · 73

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  9. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  10. 2022Planning-oriented Autonomous Drivingcited by 1,068
  11. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  12. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
38 more
  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  2. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  3. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  4. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  5. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  6. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  7. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  8. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  9. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  10. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  11. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
  12. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  13. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  14. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  15. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  16. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  17. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  18. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  19. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  20. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 287
  21. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 280
  22. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  23. 2018Learning to Drive in a Daycited by 266
  24. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  25. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  26. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  27. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  28. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  29. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
  30. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  31. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  32. 2020Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representationscited by 150
  33. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  34. 2020PnPNet: End-to-End Perception and Prediction with Tracking in the Loopcited by 143
  35. 2023StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Constructioncited by 143
  36. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  37. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 139
  38. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 116

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 25; 2026: 13.

46 papers.

Sort:

By area:

  1. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  2. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 177
  3. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 125
  4. 2024VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervisioncited by 85
  5. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  6. 2024Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Drivingcited by 67
  7. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Modelscited by 60
  8. 2024Doe-1: Closed-Loop Autonomous Driving with Large World Modelcited by 51
  9. 2025Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodalitycited by 49
  10. 2024Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Drivingcited by 46
  11. 2025HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decodercited by 35
  12. 2026SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Drivingcited by 34
34 more
  1. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  2. 2024GaussianAD: Gaussian-Centric End-to-End Autonomous Drivingcited by 31
  3. 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Predictioncited by 29
  4. 2026LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Drivingcited by 26
  5. 2025MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learningcited by 25
  6. 2025ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Drivingcited by 24
  7. 2026DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Drivingcited by 18
  8. 2024KiGRAS: Kinematic-Driven Generative Model for Realistic Agent Simulationcited by 17
  9. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  10. 2025Challenger: Affordable Adversarial Driving Video Generationcited by 16
  11. 2024Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Modelcited by 14
  12. 2025InsightDrive: Insight Scene Representation for End-to-End Autonomous Drivingcited by 14
  13. 2026Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representationcited by 13
  14. 2026DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scalecited by 12
  15. 2025RealEngine: Simulating Autonomous Driving in Realistic Contextcited by 10
  16. 2025Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Trackingcited by 9
  17. 2025SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Constructioncited by 4
  18. 2025CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous Drivingcited by 4
  19. 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Drivingcited by 4
  20. 2025WPT: World-to-Policy Transfer via Online World Model Distillationcited by 4
  21. 2026SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planningcited by 4
  22. 2024EgoFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Drivingcited by 3
  23. 2025Echo Planning for Autonomous Driving: From Current Observations to Future Trajectories and Backcited by 3
  24. 2025Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Modelscited by 3
  25. 2026Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbationscited by 3
  26. 2026VLGA: Vision-Language-Geometry-Action Models for Autonomous Drivingcited by 3
  27. 2025Autoregressive Meta-Actions for Unified Controllable Trajectory Generationcited by 2
  28. 2025Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinementcited by 2
  29. 2025Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Drivingcited by 1
  30. 2025SpaRC-AD: A Baseline for Radar-Camera Fusion in End-to-End Autonomous Drivingcited by 1
  31. 2026Not All Agents Matter: From Global Attention Dilution to Risk-Prioritized Game Planningcited by 1
  32. 2026Temporal Sampling Frequency Matters: A Capacity-Aware Study of End-to-End Driving Trajectory Predictioncited by 0
  33. 2026PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Trackingcited by 0
  34. 2026ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholdingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
  2. 2026SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation
  3. 2026SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
  4. 2026Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving
  5. 2025ExpertAD: Enhancing Autonomous Driving Systems with Mixture of Experts
  6. 2023End-to-end Autonomous Driving: Challenges and Frontiers
  7. 2026DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving
  8. 2025Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning